Research theme 01
What mechanisms are capable of generating the behavior we observe?
Multiple generative mechanisms converging on a similar observation
Different underlying mechanisms can produce observably similar behavior — a property known as equifinality. When we only see the aggregate outcome of a complex system, identifying which mechanism actually produced it is an inverse problem: we are working backward from observation to explanation.
My current research treats this as a question about plausible sets of mechanisms rather than a single best-fit answer. Using agent-based models, machine learning, and conformal prediction, I aim to characterize the range of behavioral rules that remain consistent with what we observe, rather than reporting a single overconfident explanation. This connects directly to my earlier work on information diffusion and social simulation, where the same underlying question — what process generated this outcome? — recurs across very different empirical settings.
Projects
Current-research flagship
Different generative mechanisms can produce similar observable behavior. This work investigates how machine learning and conformal prediction can be used to identify sets of plausible behavioral rules in agent-based models rather than forcing a single overconfident explanation.
Read the project ↗Publications
2026Accepted
Jayalath, C., Rand, W., Garibay, I.
Conference of the Computational Social Science Society of the Americas (CSS), Santa Fe, NM
Introduces a conformal-prediction approach to identifying plausible sets of behavioral rules in agent-based models, rather than a single point estimate.
—In preparation
Jayalath, C., Rand, W., Garibay, I.
In preparation
Applies conformal prediction to certify plausible behavioral rule sets in agent-based models of residential segregation.